Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method to implement rack-level predictive power capping and power budget allocation to processing nodes in a rack-based information handling system (IHS), the method comprising: receiving, at a rack-level management controller, a plurality of node-level power-usage data and settings from a plurality of block controllers, including a current power consumption and an initial power budget, for each processing node within the IHS, wherein the processing nodes are arranged within blocks, each block having a block controller that handles block-level power allocation and control for all processing nodes within a corresponding block, wherein the rack-level management controller is communicatively coupled to each block controller through an infrastructure manager (IM), which connects to each block controller via at least one Ethernet cable that comprises a global throttle wire directly connecting each of the block controllers within the IHS with the IM, wherein the IM is also communicatively connected to the management controller via another Ethernet cable having a global throttle wire, and each block controller is communicatively coupled to each processing node within a corresponding block via another cable having a node-level global throttle wire allocated therein; generating a power consumption profile based on the power-usage data for each of the processing nodes; identifying a total available system power of all power modules supplying power to the IHS, wherein the IHS includes a plurality of power supply units (PSU) each capable of providing a pre-determinable amount of power for use by the components of the IHS and each coupled to and controlled by a power controller; determining a system power cap for the IHS based on the power consumption profiles and the total available system power; determining a current power budget for each of the blocks and for each of the processing nodes based on an analysis of at least one of the power consumption profile, the initial power budget, the current power consumption, the system power cap, and the total available system power; dynamically regulating an amount of power budgeted and supplied to each of the processing nodes of the IHS based on the power consumption profiles and the system power cap; and in response to a detected reduction in a total amount of the available power from all available PSUs to below the system power cap, automatically reducing the system power cap and concurrently reducing one or more allocated power budgets based on an analysis of historical usage per processing node and other factors, wherein automatically reducing the system power cap comprises: generating a signal on the global throttle wire allocated within each Ethernet cable, the global throttle wire being at least one wire in each Ethernet cable that is assigned to provide communication of a global throttle power reduction (GTPR) signal from the rack-level management controller to the IM controller and from the IM controller to each block controller, wherein the block controllers within the IHS are pre-programmed to respond to an assertion of the GTPR signal on the global throttle wire by immediately throttling or substantially reducing processing operations of at least one processing node to reducing an overall power consumption within a corresponding block being controlled by the block controller.
A computer system manages power consumption in a rack of servers. A central controller gathers power usage data and initial power budgets from individual server controllers. Based on this data, it creates power consumption profiles for each server and determines the total available power from the rack's power supplies. A system-wide power cap is then calculated. Each server receives a current power budget derived from its profile, initial budget, current consumption, the system cap, and total available power. The system dynamically regulates power to each server based on its consumption profile and the overall power cap. If the power available from the power supplies drops below the system cap, the system automatically reduces the cap and server budgets based on past usage. This reduction is signaled to server controllers via a dedicated wire in Ethernet cables, prompting immediate throttling of server operations to reduce power consumption.
2. The method of claim 1 , further comprising: initializing the management controller during start-up configuration of the IHS; establishing communication between the management controller, the power subsystem, and the block controllers, which each control block-level operations of processing nodes within a corresponding block; triggering the block controllers to regulate an amount of power supplied to each of the processing nodes within an associated block based on the current power budget allocated to each of the processing nodes within the associated block; tracking, via the block controllers, the power-usage data and settings for the processing nodes within the associated block; and transmitting the power-usage data and settings from the block controllers to the management controller.
The power management system (described in claim 1) initializes the central controller during system startup. It establishes communication between the central controller, the power supplies, and the server controllers. The server controllers then regulate power to each server based on its assigned budget. They also track power usage data and settings for each server and transmit this data back to the central controller. This allows for continuous monitoring and adjustment of power allocations based on real-time consumption. The server controllers manage block-level operations for the processing nodes within the corresponding block.
3. The method of claim 1 , further comprising: detecting a current power consumption by a first processing node within the IHS; determining if an increase in the current power consumption has occurred for the first processing node; in response to determining that an increase in the current power consumption has occurred for the first processing node, determining if the required power to operate all of the processing nodes at current consumption levels is approaching the system power cap; and in response to determining that the current power consumption by all of the processing nodes is less than the system power cap: increasing the power budget of the first processing node to a new power budget and providing a corresponding increase in the first power allocation to the first processing node; and re-adjusting the power allocation across the IHS based on the new power budget.
The power management system (described in claim 1) monitors power consumption of individual servers. If a server's power usage increases, the system checks if overall power demand is approaching the system power cap. If the total power consumption is still below the cap, the system increases the server's power budget and allocates more power to it, readusting the power allocation across the entire information handling system. This allows for dynamic power allocation based on changing workloads.
4. The method of claim 3 , further comprising: determining if any of the processing nodes are using less than a pre-determined amount of their current power budget allocation over a minimum established period of time; and in response to determining that at least one second processing node is using less than the pre-determined amount of its current power budget allocation: re-apportioning at least a portion of an unused power amount from the current power budget allocated to the at least one second processing node to provide a second, higher power budget allocated to the first processing node based on the new power budget; and increasing the power budget of the first processing node to create the new power budget.
The power management system (described in claim 3) identifies servers using less than their allocated power budget for a specified time. If a server is underutilizing its budget, the system reallocates the unused portion to another server requiring more power. This dynamically adjusts power budgets, increasing the power budget of the server needing more power and creates a new power budget.
5. The method of claim 1 , further comprising: storing the power consumption profiles within a power consumption history table in a persistent storage device.
The power management system (described in claim 1) stores the power consumption profiles of the servers in a persistent storage device, creating a historical record for analysis and future power allocation decisions. The profiles are stored in a power consumption history table.
6. The method of claim 1 , further comprising: identifying a decrease in the current power consumption for the first processing node; tracking a period of time over which the decrease in the power consumption occurs; in response to the period of time not exceeding a pre-established power budget adjustment time (PBAT) threshold, maintaining the current power budget allocated to the first processing node; and in response to the period of time exceeding the pre-established PBAT threshold: reducing a value of the current power budget of the first processing node to generate a new power budget; and triggering the power subsystem of the IHS to provide a second power allocation for the first processing node based on the new power budget.
The power management system (described in claim 1) identifies servers with decreasing power consumption. It monitors the duration of the decrease. If the decrease persists beyond a predefined threshold (PBAT), the server's power budget is reduced, and the power subsystem provides a lower power allocation. If the decrease is short-lived (below PBAT), the original budget is maintained.
7. The method of claim 6 , further comprising: determining the decrease in the current power budget for the first processing node; and increasing the available amount of power within the system power cap by an amount corresponding to the decrease in the current power budget for the first processing node.
The power management system (described in claim 6) determines the amount of power freed up by reducing a server's power budget. It then increases the overall system power cap by the same amount, making the freed-up power available for reallocation.
8. The method of claim 7 , further comprising: determining a new power budget to allocate to one or more of the higher-power-usage processing nodes based on the increase in the available amount of power within the system power cap; and triggering the power subsystem of the IHS to provide the new power budget to the one or more processing nodes.
The power management system (described in claim 7) uses the increased available power within the system power cap to allocate new power budgets to servers with higher power demands. The power subsystem then provides the increased power allocations to these servers.
9. The method of claim 1 , further comprising: determining a number of PSUs from the plurality of PSUs that are required to be utilized to provide the system power cap; in response to the number of PSUs required to provide the system power cap being less than a total number of PSUs, autonomously shutting off one or more of a remaining PSUs that are not required to provide the system power cap; in response to determining that the current power consumption across the IHS exceeds a pre-established maximum percentage of the system power cap for more than a minimum pre-established threshold period of time, while there are one or more PSUs turned off, turning on at least one of the one or more PSUs to enable an increase in the system power cap and a corresponding increase in one or more allocated power budgets based on power usage factors; wherein turning on and off of one or more PSUs is performed based on an efficiency evaluation to enable efficient use of the plurality of PSUs; and in response to determining that the current power consumption across the IHS is greater than the pre-established maximum percentage of the system power cap, when all available PSUs are turned on, power capping the operations of one or more processing nodes.
The power management system (described in claim 1) calculates the minimum number of power supplies needed to meet the system power cap. If there are redundant power supplies, it automatically shuts down the unnecessary ones to improve efficiency. If the system's power consumption exceeds a threshold for a certain period, the system reactivates one or more of the shutdown power supplies. The system prioritizes the efficient use of the power supplies when turning them on or off. If all power supplies are on and power consumption is still too high, the system power caps individual server operations.
10. The method of claim 9 , wherein turning on at least one of the one or more power supplies to enable an increase in the system power cap comprises: maintaining a current system power cap while the at least one PSU is being turned on; and initiating the increase in the system power cap and subsequent increase in the allocated power budgets only after the at least one PSU has completely turned on and is supplying additional power.
In the power management system (described in claim 9), when turning on a power supply to increase the system power cap, the system maintains the current system power cap until the power supply is fully activated and providing power. Only then does the system increase the system power cap and subsequently increase the allocated power budgets.
11. An information handling system (IHS) comprising: one or more blocks, the blocks having at least one block controller and each of the blocks having one or more functional components including one or more processing nodes, the block controllers each controlling block-level operations of the processing nodes within a corresponding block; a rack-level management controller having a processor and a memory coupled to the processor, the rack-level management controller communicatively coupled to the block controllers and the processing nodes via the block controllers; a power subsystem communicatively coupled to the rack-level management controller and providing power distribution to a plurality of the functional component of the IHS; a plurality of power supply units (PSU) each capable of providing a pre-determinable amount of power for use by the components of the IHS and each coupled to and controlled by a power controller; and the rack-level management controller having firmware executing thereon to enable rack level predictive power allocation in a rack-configured IHS, wherein the firmware configures the rack-level management controller to: receive a plurality of node-level power-usage data and settings from a plurality of block controllers, including a current power consumption and an initial power budget, for each processing node within the IHS, wherein the processing nodes are arranged within blocks, each having a block controller that handles block-level power allocation and control for processing nodes within a corresponding block, wherein the rack-level management controller is communicatively coupled to each block controller, and each block controller is communicatively coupled to each processing node with a corresponding block; generate a power consumption profile based on the power-usage data for each of the processing nodes; identify a total available system power from all power modules supplying power to the IHS; determine a system power cap for the IHS based on the power consumption profiles and the total available system power; determine a current power budget for each of the processing nodes based on an analysis of at least one of the power consumption profile, the initial power budget, the current power consumption, the system power cap, and the total available system power; trigger the power subsystem of the IHS to regulate an amount of power budgeted and supplied to each of the processing nodes of the IHS based on the power consumption profiles and the system power cap; and in response to a failure of one or more of the PSUs reducing a total amount of the available power to below the system power cap, automatically reduce the system power cap and concurrently reduce one or more allocated power budgets based on an analysis of historical usage per processing node and other factors, wherein to automatically reduce the system power cap in response to a failure of one or more of the PSUs, the rack-level management controller: triggers generation of a signal on a global throttle wire allocated within each Ethernet cable directly connecting each of the block controllers within the IHS with an infrastructure manager (IM), wherein the IM is also communicatively connected to the management controller via another Ethernet cable having a global throttle wire, the global throttle wire being at least one wire in each Ethernet cable that is assigned to provide communication of a global throttle power reduction (GTPR) signal from the rack-level management controller to the IM controller and from the IM controller to each block controller, wherein the block controllers within the IHS are pre-programmed to respond to an assertion of the GTPR signal on the global throttle wire by immediately reducing the current power consumption of one or more processing nodes within a respective block being controlled by the block controller.
A server rack includes multiple server blocks, each with its own controller managing the servers within. A central rack-level controller, with processor and memory, communicates with the block controllers and manages overall power. A power subsystem distributes power from multiple power supplies. The rack-level controller runs firmware that gathers power usage from the block controllers, creates server power profiles, and determines the total available power. It then calculates a system power cap and assigns power budgets to each server. The subsystem regulates power to servers based on their profiles and the system cap. If a power supply fails, reducing available power, the controller automatically reduces the power cap and server budgets. It signals this reduction to block controllers via a dedicated wire in Ethernet cables, prompting immediate power reduction in the affected servers.
12. The information handling system of claim 11 , further comprising initializing the rack-level management controller during start-up configuration of the IHS; the block controllers having firmware executing thereon, wherein the firmware configures the block controllers to: regulate an amount of power supplied to each of the processing nodes within an associated block based on the current power budget allocated to each of the processing nodes within the associated block; track the power-usage data and settings for the processing nodes within the associated block; and transmit the power-usage data and settings from the block controllers to the management controller.
The information handling system (described in claim 11) initializes the rack-level management controller during system startup. The block controllers run firmware that regulates power supplied to each server based on its assigned budget, tracks power usage data and settings, and transmits this data to the management controller.
13. The information handling system of claim 11 , further comprising: a first block controller detecting a current power consumption by a first processing node within the IHS and the first block controller determining if an increase in the current power consumption has occurred for the first processing node; in response to the first block controller determining that an increase in the current power drawn has occurred for the first processing node, the firmware further configures the rack-level management controller to: determine if the required power to operate all of the processing nodes at current consumption levels is approaching the system power cap; and in response to determining that the current power consumption by all of the processing nodes is less than the system power cap: increasing the power budget of the first processing node to a new power budget and providing a corresponding increase in the first power allocation to the first processing node; and re-adjusting the power allocation across the IHS based on the new power budget.
In the information handling system (described in claim 11), a block controller detects an increase in power consumption by a server. If an increase occurs, the rack-level management controller determines if the total power required is approaching the system power cap. If total consumption is below the cap, the system increases the server's power budget and re-adjusts power allocation across the rack.
14. The information handling system of claim 11 , wherein the firmware further configures the rack-level management controller to: determine if any of the processing nodes are using less than a pre-determined amount of their current power budget allocation over a minimum established period of time; and in response to determining that at least one second processing node is using less than the pre-determined amount of its current power budget allocation: increase the power budget of the first processing node to create the new power budget; and re-apportion at least a portion of an unused power amount from the current power budget allocated to the at least one second processing node to provide a second, higher power budget allocated to the first processing node based on the new power budget.
In the information handling system (described in claim 11), the firmware on the rack-level management controller checks if any servers are consistently using less power than their allocated budget. If so, the system reallocates the unused power to another server that needs more power, increasing the power budget of that server.
15. The information handling system of claim 11 , wherein the firmware further configures the rack-level management controller to: store the power consumption profiles within a power consumption history table in a persistent storage device.
The information handling system (described in claim 11) stores server power consumption profiles in a persistent storage device (a power consumption history table) for later analysis and optimization.
16. The information handling system of claim 11 , wherein the firmware further configures the rack-level management controller to: identify a decrease in the current power consumption for the first processing node; track a period of time over which the decrease in the power consumption occurs; in response to the period of time not exceeding a pre-established power budget adjustment time (PBAT) threshold, maintaining the current power budget allocated to the first processing node; and in response to the period of time exceeding the pre-established PBAT threshold: reduce a value of the current power budget of the first processing node to generate a new power budget; and trigger the power subsystem of the IHS to provide a second power allocation for the first processing node based on the new power budget.
In the information handling system (described in claim 11), the firmware on the rack-level management controller identifies a server experiencing a decrease in power consumption. It tracks the duration of this decrease. If the decrease lasts longer than a specified time (PBAT), the server's power budget is reduced, and the power subsystem provides a lower power allocation.
17. The information handling system of claim 16 , wherein the firmware further configures the rack-level management controller to: determine the decrease in the current power budget for the first processing node; and increase the available amount of power within the system power cap by an amount corresponding to the decrease in the current power budget for the first processing node.
In the information handling system (described in claim 16), the firmware on the rack-level management controller calculates the amount of power saved by reducing a server's budget. It then increases the overall system power cap by that amount.
18. The information handling system of claim 17 , wherein the firmware further configures the rack-level management controller to: determine a new power budget to allocate to one or more of the processing nodes based on the increase in the available amount of power within the system power cap; and trigger the power subsystem of the IHS to provide the new power budget to the one or more processing nodes.
In the information handling system (described in claim 17), the firmware on the rack-level management controller determines new power budgets for other servers based on the increased available power and triggers the power subsystem to allocate these new budgets.
19. The information handling system of claim 11 , wherein: the firmware further configures the rack-level management controller to: determine a number of PSUs from the plurality of PSUs that are required to be utilized to provide the system power cap; in response to the number of PSUs required to provide the system power cap being less than a total number of PSUs, autonomously shut off one or more of a remaining PSUs that are not required to provide the system power cap; in response to determining that the current power consumption across the IHS exceeds a pre-established maximum percentage of the system power cap for more than a minimum pre-established threshold period of time, while there are one or more PSUs turned off, turn on at least one of the one or more PSUs to enable an increase in the system power cap and a corresponding increase in one or more allocated power budgets based on power usage factors; wherein turning on and off of one or more PSUs is performed based on an efficiency evaluation to enable efficient use of the plurality of PSUs; and in response to determining that the current power consumption across the IRS is greater than the pre-established maximum percentage of the system power cap, when all available PSUs are turned on, power cap the operations of one or more processing nodes.
In the information handling system (described in claim 11), the firmware on the rack-level management controller calculates the minimum number of power supplies needed. If there are extra power supplies, it shuts them down. If power consumption increases beyond a threshold, the controller turns on additional power supplies. The power supplies are turned on and off based on an efficiency evaluation to maximize energy savings. When all power supplies are active, the system power caps individual server operations if needed.
20. The information handling system of claim 19 , wherein turning on at least one of the one or more power supplies to enable an increase in the system power cap causes the firmware to further configure the rack-level management controller to: maintain a current system power cap while the at least one PSU is being turned on; and initiate the increase in the system power cap and subsequent increase in the allocated power budgets only after the at least one PSU has completely turned on and is supplying additional power.
In the information handling system (described in claim 19), when the firmware on the rack-level management controller turns on an additional power supply, it maintains the current system power cap until the power supply is fully operational and providing power. Only then does it increase the system power cap and subsequent power budgets.
Unknown
September 5, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.